Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 365 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1688. Min Act: -0.0003

Data Index: 1254020 (C4 (Web Text))

Max Activating Token Index: 458

Text #1

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1593. Min Act: -0.0003

Data Index: 4255 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1577. Min Act: -0.0003

Data Index: 506043 (C4 (Web Text))

Max Activating Token Index: 640

Text #3

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1569. Min Act: -0.0003

Data Index: 1048365 (C4 (Web Text))

Max Activating Token Index: 117

Text #4

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1503. Min Act: -0.0003

Data Index: 495156 (C4 (Web Text))

Max Activating Token Index: 228

Text #5

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1496. Min Act: -0.0003

Data Index: 285585 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1454. Min Act: -0.0003

Data Index: 654022 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1462. Min Act: -0.0003

Data Index: 71716 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1420. Min Act: -0.0003

Data Index: 1071030 (C4 (Web Text))

Max Activating Token Index: 344

Text #9

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1442. Min Act: -0.0002

Data Index: 556947 (C4 (Web Text))

Max Activating Token Index: 286

Text #10

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1419. Min Act: -0.0002

Data Index: 1074885 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1404. Min Act: -0.0003

Data Index: 1034263 (C4 (Web Text))

Max Activating Token Index: 270

Text #12

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1382. Min Act: -0.0003

Data Index: 961354 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1363. Min Act: -0.0003

Data Index: 752330 (C4 (Web Text))

Max Activating Token Index: 656

Text #14

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1361. Min Act: -0.0003

Data Index: 309469 (C4 (Web Text))

Max Activating Token Index: 760

Text #15

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1361. Min Act: -0.0003

Data Index: 855762 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1315. Min Act: -0.0003

Data Index: 523305 (C4 (Web Text))

Max Activating Token Index: 564

Text #17

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1361. Min Act: -0.0003

Data Index: 1254358 (C4 (Web Text))

Max Activating Token Index: 661

Text #18

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1347. Min Act: -0.0003

Data Index: 180198 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 0.1688. Min Range: -0.1688

Max Act: 0.1285. Min Act: -0.0003

Data Index: 619485 (C4 (Web Text))

Max Activating Token Index: 631